@su-record/vibe 2.5.2 → 2.5.4

package/commands/vibe.spec.md

@@ -264,7 +264,14 @@ Read ~/.claude/vibe/languages/typescript-react.md
 
 ### 3. Parallel Research (v2.5.0) - MANDATORY AFTER requirements confirmed
 
-**🚨 CRITICAL: Research is MANDATORY after requirements are confirmed**
+**🚨🚨🚨 ABSOLUTE RULE: YOU MUST USE BASH TOOL FOR RESEARCH 🚨🚨🚨**
+
+**STOP! Before doing ANY research, read this carefully:**
+
+1. **DO NOT** use Task tool to spawn research agents
+2. **DO NOT** use context7 MCP directly for research
+3. **DO NOT** use WebSearch tool directly for research
+4. **YOU MUST** use Bash tool to call the orchestrator command below
 
 **When to trigger:**
 1. ✅ Feature type decided (e.g., "passkey authentication")
@@ -272,27 +279,33 @@ Read ~/.claude/vibe/languages/typescript-react.md
 3. ✅ Language guide copied (step 2.5)
 4. ✅ Core requirements collected
 
-**→ IMMEDIATELY run orchestrator research. NO EXCEPTIONS.**
+**→ IMMEDIATELY execute this EXACT Bash command (replace placeholders):**
 
-**Execution via Orchestrator (4 agents + Multi-LLM in parallel):**
 ```bash
 node -e "import('@su-record/vibe/orchestrator').then(o => o.research('[FEATURE]', ['[STACK1]', '[STACK2]']).then(r => console.log(r.content[0].text)))"
 ```
 
-**Example:**
+**Concrete example - copy, modify, and run via Bash tool:**
 ```bash
-# After confirming: passkey auth + React + Supabase
 node -e "import('@su-record/vibe/orchestrator').then(o => o.research('passkey authentication', ['React', 'Supabase']).then(r => console.log(r.content[0].text)))"
 ```
 
-**What runs in parallel (180s timeout each):**
+**WHY: The orchestrator runs 8 parallel research tasks including GPT and Gemini for 3-way validation.**
+
+**What the orchestrator runs in parallel:**
+
+| Component | Role | Source |
+|-----------|------|--------|
+| Claude Agent: `best-practices-agent` | Best practices for [feature] + [stack] | WebSearch |
+| Claude Agent: `framework-docs-agent` | Latest docs via context7 | context7 MCP |
+| Claude Agent: `codebase-patterns-agent` | Similar patterns in existing codebase | Glob, Grep |
+| Claude Agent: `security-advisory-agent` | Security advisories for [feature] | WebSearch |
+| **GPT: Best Practices** | Architecture patterns, code conventions | GPT API |
+| **GPT: Security** | CVE database, vulnerability details | GPT API |
+| **Gemini: Best Practices** | Latest trends, framework updates | Gemini API |
+| **Gemini: Security** | Latest security advisories, patches | Gemini API |
 
-| Agent | Role | Tools |
-|-------|------|-------|
-| `best-practices-agent` | Best practices for [feature] + [stack] | WebSearch |
-| `framework-docs-agent` | Latest docs via context7 | context7 MCP |
-| `codebase-patterns-agent` | Similar patterns in existing codebase | Glob, Grep |
-| `security-advisory-agent` | Security advisories for [feature] | WebSearch |
+**🚨 IF YOU USE TASK TOOL INSTEAD OF BASH, GPT/GEMINI WILL NOT BE CALLED! 🚨**
 
 #### 3.1 Multi-LLM Research Enhancement (v2.5.0)
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@su-record/vibe",
-  "version": "2.5.2",
+  "version": "2.5.4",
   "description": "Vibe - Claude Code exclusive SPEC-driven AI coding framework with 35+ integrated tools",
   "type": "module",
   "main": "dist/cli/index.js",